CN115552230A

CN115552230A - Method of monitoring surface condition of component

Info

Publication number: CN115552230A
Application number: CN202180032474.2A
Authority: CN
Inventors: 雅各布·林德利; 菲利普·施密特; 米兰达·皮泽拉; 马克·D·埃弗利
Original assignee: Watlow Electric Manufacturing Co
Current assignee: Watlow Electric Manufacturing Co
Priority date: 2020-05-02
Filing date: 2021-05-03
Publication date: 2022-12-30
Anticipated expiration: 2041-05-03
Also published as: TW202334491A; TWI792294B; US11618946B2; TW202214899A; JP2023524099A; US20210340669A1; US20230203648A1; KR20230004861A; CN115552230B; WO2021225947A1; EP4143551A1

Abstract

One method comprises the following steps: the method includes providing thermal energy to the component, determining a thermal response of the component in response to providing the thermal energy, and determining a thermal characteristic of the component based on a reference thermal response and the thermal response. The method includes predicting a surface condition of the component based on the thermal characteristic and a predictive analysis model, wherein the predictive analysis model correlates the thermal characteristic of the component to an estimated surface condition of the component.

Description

Method of monitoring surface condition of component

Cross Reference to Related Applications

This application claims priority to U.S. provisional application No. 63/019267, filed on day 2, month 5, 2020. The disclosure of the above application is incorporated herein by reference.

Technical Field

The present disclosure relates generally to a method of monitoring surface conditions of a component in a thermal system, such as a showerhead and/or a pedestal within a semiconductor processing chamber.

Background

The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.

The emissivity of a material is its effectiveness as a thermal radiation emission energy. The emissivity of the surface of the system component may change over time. For example, in semiconductor processing chambers that perform various deposition processes, chemical reactions of the deposited material typically occur in the semiconductor processing chamber and may cause the deposited material to undesirably deposit on the chamber walls, liners, and lids. In fluid conduits, dirt may undesirably accumulate on the surfaces of the fluid conduits. The emissivity of the surfaces of the system components may be progressively affected by the accumulation of deposits or dirt. When system components are used to generate or transfer heat, variations in emissivity of surfaces of the system components may affect the desired heat output and performance of the system components.

However, the variation of the surface emissivity of the system components is generally not well understood. When system components degrade significantly due to changes in emissivity, system maintenance is required to replace the degraded components, resulting in unexpected downtime. In order to maintain performance of the system components and/or reduce/inhibit downtime, preventative maintenance typically schedules cleaning, refurbishment, or replacement of critical components based on a desired rate of change rather than on actual demand. Thus, preventative maintenance may be performed too late or too early.

The problem of detecting changes in surface emissivity of components of an apparatus is addressed by the present disclosure, among other problems.

Disclosure of Invention

In one form, a method comprises: the method includes providing thermal energy to the component, determining a thermal response of the component in response to providing the thermal energy, and determining a thermal characteristic of the component based on a reference thermal response and the thermal response. The method includes predicting a surface condition of the component based on the thermal characteristic and a predictive analysis model, wherein the predictive analysis model correlates the thermal characteristic of the component to an estimated surface condition of the component.

In one form, the thermal characteristic is based on a difference between the reference thermal response and the thermal response.

In one form, the thermal characteristic is an emissivity of the component, a thermal coupling between different regions of the component, a thermal gain of the component, a resistance-temperature dependence of the component, a gas convection coupling of the component, or a combination thereof.

In one form, providing thermal energy to the component further comprises increasing the thermal energy provided to the component.

In one form, providing thermal energy to the component further comprises reducing the thermal energy provided to the component.

In one form, the surface condition represents an amount of material accumulated on a surface of the component.

In one form, the thermal response is the rate of thermal energy dissipation through the component.

In one form, the method further comprises varying at least one of the intensity and duration of the thermal energy to create a thermal signature of the component, wherein the thermal signature is an image representation of the thermal response.

In one form, the method further includes determining a thermal characteristic of the component based on the reference thermal signature and the thermal signature.

In one form the component is selected from the group consisting of a wall of a semiconductor processing chamber, a liner of a semiconductor processing chamber, a showerhead of a semiconductor processing chamber, a lid of a semiconductor processing chamber, a wall of a fluid heating conduit, a heater surface, and a heater jacket.

In one form, the method further includes measuring a temperature of the component during a predetermined period of time to determine the thermal response.

In one form, the method further includes determining an energy dissipation of the component based on a change in temperature of the component during a predetermined period of time.

In one form, the method further includes determining a change in emissivity of the component based on a change in temperature of the component during a predetermined period of time.

In one form, the thermal response of the component is determined in response to the temperature of the component equaling a predetermined temperature.

The present disclosure provides a system comprising a component, a thermal control system configured to provide thermal energy to the component, and a controller. The controller is configured to determine a thermal response of the component in response to providing the thermal energy, wherein the thermal response is a rate of dissipation of the thermal energy through the component. The controller is configured to determine a thermal characteristic of the component based on a reference thermal response and a difference between the thermal response, wherein the reference thermal response is a reference dissipation rate of the component thermal energy in response to providing the thermal energy. The controller is configured to predict an amount of material accumulation on a surface of the component based on the thermal characteristic and a predictive analysis model, wherein the predictive analysis model correlates the thermal characteristic of the component to an estimated surface condition of the component.

In one form, the thermal characteristic is an emissivity of the component, a thermal coupling between different regions of the component, a thermal gain of the component, a resistance-temperature dependence of the component, a gas-convective coupling of the component, or a combination thereof.

In one form, the thermal control system further comprises a heater configured to provide thermal energy to the component.

In one form, the predictive analysis model is generated during a training routine.

In one form the component is a semiconductor processing system component.

Further areas of applicability will become apparent from the description provided herein. It should be understood that the description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure.

Drawings

In order that the disclosure may be well understood, various forms thereof will now be described, by way of example, with reference to the accompanying drawings, in which:

FIG. 1 is an example semiconductor processing laboratory according to the teachings of the present disclosure;

FIG. 2 is a diagram of a semiconductor processing chamber and monitoring system according to the teachings of the present disclosure;

FIG. 3 is a functional block diagram of a thermal response determination module according to the teachings of the present disclosure;

FIG. 4A is a graphical illustration of a measured thermal response and a reference thermal response of a component according to the teachings of the present disclosure;

FIG. 4B is a graphical illustration of a measured thermal response of a plurality of components and a reference thermal response of the components according to the teachings of the present disclosure;

FIG. 5 is a flow diagram of an exemplary training routine performed by the monitoring system in accordance with the teachings of the present disclosure; and

fig. 6 is a flow diagram of an example surface condition prediction routine executed by a monitoring system according to the teachings of the present disclosure.

The drawings described herein are for illustration purposes only and are not intended to limit the scope of the present disclosure in any way.

Detailed Description

The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, or uses. It should be understood that throughout the drawings, corresponding reference numerals indicate like or corresponding parts and features.

The present disclosure provides a monitoring system configured to monitor a thermal characteristic (such as emissivity) of a component to predict a surface condition of the component. For example, in a semiconductor processing system, coking in the heater or other components of the semiconductor processing system may increase emissivity and decrease convective heat transfer rates, causing the heater to operate at higher temperatures and with increased energy consumption. The monitoring system of the present disclosure can accurately detect coking in heaters or other components of a semiconductor processing system and alert an operator and/or system controller of the detected condition. In addition, the monitoring system can accurately locate material buildup on various components of the semiconductor processing system, thereby enabling an operator and/or system controller to adapt and/or remedy the material buildup in implementing control parameters for the semiconductor manufacturing process routine.

More specifically, in one form, a monitoring system provides thermal energy to a component, determines a thermal response of the component in response to providing the thermal energy, and determines a thermal characteristic of the component based on a reference thermal response and the thermal response. The monitoring system then predicts a surface condition of the component based on the thermal characteristic and a predictive analysis model, wherein the predictive analysis model correlates the plurality of thermal characteristics of the component to a plurality of estimated surface conditions of the component.

Referring to fig. 1, in one example application, the control system of the present disclosure is disposed in a semiconductor processing system 10 that includes at least one chamber 2 having one or more heaters (not shown) disposed therein. Although not shown, one or more control systems are provided to control the heaters. The semiconductor processing system 10 includes other subsystems for processing semiconductor wafers, and those subsystems may affect the thermal response of the heaters. For example, a fluid line system having a transfer line 4 and a vent line 6 delivers process gases to and from the chamber 2.

Referring to fig. 2, the semiconductor processing system 10-1 is further configured to monitor the surface condition of the component and includes at least one heater 14, a plurality of temperature sensors 16, and a monitoring system 18 for monitoring and predicting the surface condition of the component. In one form, the components may be various system components of the semiconductor processing chamber 22 and/or heating conduits of the semiconductor processing system 10-1. By way of example, the component may be a wall 12-1 of the semiconductor processing chamber 22, a liner 12-2 of the semiconductor processing chamber 22, a showerhead 12-3 of the semiconductor processing chamber 22, a lid 12-4 of the semiconductor processing chamber 22, a wall 12-5 of the fluid heating conduit 26, a top layer 12-6 of the wafer support pedestal 20, a surface of the heater 14, and/or a jacket 12-7 of the heater 14 (collectively/individually and hereinafter referred to as "component 12").

In one form, the surface condition of the component 12 may be the amount of material accumulated or deposited on the surface of the component 12. In one form, the material accumulation or deposition affects the emissivity of the surface of the component 12 and the heat transfer from the surface of the component 12 to the ambient environment (e.g., a wafer disposed on the wafer support pedestal 20). Accordingly, the monitoring system 18 is configured to monitor changes in the thermal properties of the surface of the component 12, thereby predicting the state and/or amount of material accumulation and deposition on the surface of the component 12, as described in further detail below. In one form, the thermal properties include, but are not limited to: emissivity of component 12, thermal coupling between multiple regions of component 12, thermal gain of component 12, resistance-temperature dependence of component 12, and gas convection coupling of component 12. It should be understood that various other thermal characteristics may be determined and the disclosure is not limited to the example thermal characteristics described herein.

In one form, the at least one heater 14 may be built into the component 12 or disposed external to the component 12. In one form, the at least one heater 14 may be configured to provide thermal energy to the component 12. As used herein, "providing thermal energy to the component 12" refers to increasing or decreasing the thermal energy provided to a surface of the component 12 and/or an environment proximate (i.e., adjacent and/or near) the component 12. As an example, increasing the thermal energy provided to component 12 may include heating the surface of component 12 and/or the environment proximate component 12. As another example, reducing the thermal energy provided to the component 12 may include cooling the surface of the component 12 and/or the environment proximate the component 12. Although the semiconductor processing system 10-1 is shown as including at least one heater 14, it should be understood that the heater 14 may be removed from the semiconductor processing system 10-1 when thermal energy is provided externally to a fluid (e.g., gas) through a fluid heating conduit 26 to provide plasma into the semiconductor processing chamber 22.

In one form, a plurality of temperature sensors 16 may be built into the component 12 or disposed external to the component 12 for measuring the temperature of the surface of the component 12 and/or the surrounding environment. By way of example, the temperature sensors 16 may include, but are not limited to: thermocouples, resistance Temperature Detectors (RTDs), infrared sensors, and/or other conventional temperature sensing devices. In one form, the temperature sensor 16 is a "two wire" heater built into the component 12 (e.g., the wafer support pedestal 20). The two-wire heater includes a resistive heating element as a heater and a temperature sensor with only two leads (instead of four) operatively connected to the heating element. Such two-wire capability is disclosed, for example, in U.S. patent No. 7196295, which is commonly assigned with the present application and incorporated herein by reference in its entirety. Typically, in a two wire system, the resistive heating element is defined by a material that exhibits a resistance that varies with changing temperature, such that an average temperature of the resistive heating element is determined based on the change in resistance of the resistive heating element. In one form, the resistance of the resistive heating element is calculated by first measuring the voltage across the heating element and the current through the heating element and then determining the resistance of the resistive heating element using ohm's law. The resistive heating element may be defined by a relatively high Temperature Coefficient of Resistance (TCR) material, a negative TCR material, or in other words a material having a non-linear TCR.

In one form, the monitoring system 18 includes a thermal control system 30, a thermal response determination module 32, a characteristics module 34, a surface conditions module 36, a predictive analysis model database 38, an alarm module 40, a surface conditions verification module 42, and a surface conditions reference table database 44. It should be readily appreciated that any of the modules, systems, and/or databases of the monitoring system 18 may be provided at the same location or distributed at different locations (e.g., by one or more edge computing devices) and communicatively coupled accordingly. Although the monitoring system 18 is shown as part of the semiconductor processing system 10-1, it should be understood that the monitoring system 18 may be remote from the semiconductor processing system 10-1. In one form, the monitoring system 18 and the temperature sensor 16 use a wired communication protocol and/or a wireless communication protocol (e.g.,

type protocolA cellular protocol, a wireless fidelity (Wi-Fi) type protocol, a Near Field Communication (NFC) protocol, an ultra-wideband (UWB) protocol, etc.).

In one form, the thermal control system 30 is configured to control operation of the heater 14 and/or the flow of fluid provided into the semiconductor processing chamber 22 through the fluid heating conduit 26. As an example, the thermal control system 30 may include a power supply and one or more power converter circuits to provide power to the heater 14, and thus thermal energy to the component 12. Accordingly, to perform the functions described herein, the thermal control system 30 may include one or more processors configured to execute instructions stored in a non-transitory computer readable medium (e.g., random Access Memory (RAM) and/or Read Only Memory (ROM)) and control the power converter circuitry and the power supply. As another example, the thermal control system 30 may control a Radio Frequency (RF) plasma generator (not shown) to increase/decrease the thermal energy provided to the fluid heating conduit 26. In one form, the thermal control system 30 provides thermal energy until a set point temperature of the component 12, the ambient environment of the component 12, and/or another component of the semiconductor processing chamber 22 is reached. In one variation, the monitoring system 18 communicates with a thermal control system 30 or a controller thereof provided in an existing semiconductor processing system.

In one form, the thermal response determination module 32 is configured to receive temperature data obtained by the temperature sensor 16 and determine the thermal response of the component 12 in response to the thermal control system 30 providing thermal energy to the component 12. In one form, the thermal response of the component 12 refers to the rate at which the component 12 dissipates thermal energy to the surrounding environment after thermal energy is provided to the component 12. As an example, the thermal response determination module 32 is configured to determine a rate at which the component 12 dissipates thermal energy as a function of temperature changes over a given period of time. In some forms, the thermal response may be determined when the temperature of the component 12 is equal to a predetermined temperature and/or during a predetermined time period, as described in further detail below. In one form, thermal response refers to system parameters that provide thermal energy (e.g., voltage, current, resistance, and/or other parameters of the heater 14 when thermal energy is provided).

In one form and as shown in fig. 3A, the characterization module 34 is configured to determine thermal characteristics of the component 12 and includes a reference emissivity model database 52, a reference thermal coupling model database 54, a reference thermal gain model database 56, a reference RT correlation model database 58, a reference gas convective coupling model database 60, a reference thermal signature database 61, and a thermal characterization module 62.

In one form, the reference emissivity model database 52 stores a reference emissivity model for the component 12. As an example, the reference emissivity model may represent the emissivity of the component 12 when there is no accumulation of material on the surface of the component 12. It should be understood that the reference emissivity model database 52 may include an additional reference emissivity model that represents the emissivity of the component 12 when a predetermined amount of material accumulates on the surface of the component 12.

In one form, the reference thermal coupling model database 54 stores reference thermal coupling models for the components 12. As an example, when there is no accumulation of material on the surface of the component 12, the reference thermal coupling model may represent the thermal coupling between the component 12 and another component (e.g., conduction, convection, and radiation rates between two adjacent and/or spaced apart components 12 and/or the heater 14). It should be understood that the reference thermal coupling model database 54 may include additional reference thermal coupling models that represent the thermal coupling of the component 12 with various components within the semiconductor processing system 10-1 and/or the amount of various material buildup located on the surface of the component 12.

In one form, the reference thermal gain model database 56 stores a reference thermal gain model for the component 12. As an example, the reference thermal gain model may represent the thermal gain of the component 12 at a given temperature when there is no material accumulation on the surface of the component 12. It should be understood that the reference thermal gain model database 56 may include additional reference thermal gain models that represent the thermal gain of the component 12 at various temperatures and/or various amounts of material buildup located on the surface of the component 12.

In one form, the reference RT correlation model database 58 stores a reference resistance-temperature correlation model for the component 12. As an example, the reference resistance temperature-dependent model may represent a correlation between resistance and temperature of the component 12 when there is no material accumulation on the surface of the component 12. It should be understood that the reference RT correlation model database 58 may include additional reference resistance-temperature models that represent the resistance-temperature correlation of the component 12 when a predetermined amount of material buildup is located on the surface of the component 12.

In one form, the reference gas convection coupling model database 60 stores reference gas convection coupling models for the component 12. As an example, the reference gas convective coupling model may represent heat transfer from a fluid (e.g., a gas) provided to the component 12 through the fluid heating conduit 26 and/or the plasma when there is no material accumulation on the surface of the component 12. It should be understood that the reference gas convection coupling model database 60 may include additional reference gas convection coupling models that represent heat transfer from a fluid (e.g., gas) provided through the fluid heating conduit 26 and/or plasma to the component 12 when a predetermined amount of material buildup is located on the surface of the component 12.

In one form, the reference emissivity model, the reference thermal coupling model, the reference thermal gain model, the reference RT correlation model, and the reference gas convection coupling model (collectively referred to herein as the "reference model") are generated during a calibration routine performed by the monitoring system 18 and/or during a machine learning routine performed by the surface conditions module 36, as described in further detail below.

In one form, the reference thermal signature database 61 stores reference thermal signatures for the components 12. As an example, the reference thermal signature is an image representation of a thermal response when varying at least one of the intensity and duration of thermal energy provided to the component 12 when no material accumulates on the surface of the component 12. It should be understood that the reference thermal signature database 61 may store additional reference thermal signatures of the component 12 corresponding to a predetermined amount of material buildup on the surface of the component 12.

In one form, the thermal characteristics module 62 is configured to determine the thermal characteristics of the component 12 based on differences between the thermal response and one or more of the reference models. In one form, the thermal characterization module 62 may compare the thermal response to a reference emissivity model to determine if the emissivity of the component 12 has changed. As an example and as shown in the graph 100 of FIG. 4A, the thermal characterization module 62 may determine that the emissivity of the component 12 has changed based on a reference emissivity model 102 of the component 12 and a thermal response 104 of the component 12, which shows a lower maximum temperature and a faster rate of temperature decay over a given period of time.

As another example and as shown in graph 110 of fig. 4B, a second component (e.g., heater 14) of the semiconductor processing system 10 may receive thermal energy and the temperature sensor 16 may monitor a rate of change of temperature of the second component as indicated by the thermal response 112. Further, the reference emissivity model 116 may correspond to an expected thermal response of the given component 12 when the second component receives thermal energy. Accordingly, the thermal characterization module 62 may determine, based on the thermal response 114, that the emissivity of the component 12 has changed, which shows a higher local maximum temperature over a given period of time.

As another example, thermal characterization module 62 may create a thermal signature of component 12 based on the thermal response data and compare the thermal signature to one or more of the reference thermal signatures to determine whether the emissivity, thermal coupling, etc. of component 12 has changed. In one form, the thermal signature of the shorter energy pulse is associated with a closely related signature of the heating element (e.g., a signature in the heater jacket or conductive contacts), and the thermal signature of the longer energy pulse is associated with a higher decoupling (e.g., a signature that heats radiantly). It should be understood that thermal characteristic module 62 may compare the thermal response to any of the reference models to determine if there is a change in the corresponding thermal characteristic.

Referring back to FIG. 2, the surface condition module 36 is configured to predict the surface condition of the component 12 based on the thermal characteristics. Further, the surface condition module 36 is configured to predict the surface condition based on at least one of the surface condition reference table stored in the surface condition reference table database 44 and the predictive analysis model stored in the predictive analysis model database 38.

In one form, the surface condition reference table is a look-up table that correlates various thermal characteristics of the component 12 to various empirically obtained surface conditions of the component 12. Thus, an operator may generate a look-up table by depositing various known quantities and/or distribution patterns (patterns) of material onto the component 12 and, for example, comparing the emissivity change of the known quantities of material to a reference emissivity model. Accordingly, surface condition module 36 may reference the surface condition reference table to identify a corresponding thermal property change (e.g., emissivity change) and predict a corresponding surface condition of component 12 (e.g., an amount and/or distribution of material buildup on a surface of component 12). In some forms, monitoring system 18 may not have a surface condition reference table database 44 to store the surface condition reference table.

In one form, the predictive analysis model relates various thermal characteristics of the component 12 to various estimated surface conditions of the component 12. In one form, the surface condition module 36 may include an artificial neural network, a convolutional neural network, and/or other similar machine learning computing system configured to execute machine learning routines (such as supervised learning routines, unsupervised learning routines, reinforcement learning routines, self-learning routines, black box modeling routines, etc.) to generate predictive analytics models. During the machine learning routine, the thermal control system 30 may provide thermal energy to the component 12 via pulses, steps (steps) or ramps (ramps) at periodic or aperiodic timings and/or varying amplitudes. Thus, a supervised learning routine may be performed such that behavior due to unknown model parameters (e.g., applied power, gas flow adjacent to the component 12, gas pressure adjacent to the component 12, thermal energy in pulses, steps, ramps, periodic or aperiodic timing, varying amplitude of thermal energy pulses) is represented in the thermal response.

As an example, when the surface condition module 36 executes a supervised learning routine, the known amounts and/or distributions of materials on the surface of the component 12 are used to develop a predictive analysis model that relates the amount/distribution of materials and/or other unknown model parameters to changes in thermal properties (e.g., changes in thermal coupling). Further, a supervised learning routine may be iteratively performed for various quantities/distributions to improve the accuracy of the predictive analysis model.

As another example, when the surface condition module 36 executes an unsupervised learning routine (e.g., the surface condition module 36 is an automated encoder neural network executing an unsupervised learning routine), the unknown quantity and/or distribution of material deposited on the component 12 is used to develop a predictive analysis model that relates the quantity/distribution of material and/or other unknown model parameters to changes in thermal properties (e.g., emissivity changes).

Accordingly, the predictive analysis model enables surface condition module 36 to predict surface conditions based on changes in emissivity (or other thermal property changes) of component 12. As an example, surface condition module 36 correlates the determined emissivity change of component 12 with a predictive analysis model to predict whether the emissivity change is "normal" (i.e., the heat dissipation rate is within a predetermined and/or expected range due to a reduction or less than an expected material accumulation on the surface of component 12) or "abnormal" (i.e., the heat dissipation rate is greater than the predetermined and/or expected range due to an increase or more than an expected material accumulation on the surface of component 12). It should be understood that surface condition module 36 may characterize component 12 using various other qualitative and/or quantitative characterization based on predictive analysis models, and is not limited to the examples described herein.

In one form, the alarm module 40 includes various user interfaces for indicating the presence of material buildup on the surface of the component 12. As examples, the alert module 40 may include various visual interfaces (e.g., a touch screen, a display monitor, an augmented reality device, and/or a plurality of Light Emitting Diodes (LEDs)), an audible interface (e.g., speaker circuitry for audibly outputting a message corresponding to a material accumulation), and/or a tactile interface (e.g., a vibrating motor circuit that vibrates when the material accumulation is greater than a threshold value).

In one form, the surface condition verification module 42 is configured to verify and/or calibrate the predictive analysis model and/or the surface condition reference table when the alarm module 40 outputs a signal indicative of material buildup on the surface of the component 12. By way of example, the surface condition verification module 42 includes a visual interface (such as a touch screen device) that is provided to an operator to view the predicted amount/distribution of material accumulation and verification. Additionally, the visual interface of the surface condition verification module 42 may include one or more graphical elements operable to enable an operator to verify the prediction and/or adjust parameters of the predictive analysis model and/or the surface condition reference table. In some forms, the monitoring system 18 may not have a surface condition verification module 42 for monitoring the surface condition of the component 12.

Referring to FIG. 5, a flow diagram illustrating an example training routine 500 is shown. At 504, the thermal control system 30 or an operator thereof selects thermal energy parameters (e.g., pulse, amplitude, duration, etc.). Optionally, when executing the supervised learning routine, the surface condition module 36 or an operator thereof selects surface condition parameters (e.g., amount and/or distribution of material buildup on the component 12) at 506. At 508, the thermal control system 30 provides thermal energy to the component 12, and at 512 the thermal response determination module 32 determines the thermal response of the component 12.

At 516, the characterization module 34 determines whether a reference model associated with the component 12 and/or thermal response is stored in a corresponding database (i.e., one of the reference emissivity model database 52, the reference thermal coupling model database 54, the reference thermal gain model database 56, the reference RT correlation model database 58, the reference gas convection coupling model database 60, and the reference thermal signature database 61). If so, the routine 500 proceeds to 520. Otherwise, if no reference model is stored in the corresponding database, the routine 500 proceeds to 518, at 518, the characterization module 34 generates and stores a reference thermal response for the given thermal energy parameter and then proceeds to 532.

At 520, characteristics module 34 determines thermal characteristics of component 12 based on the thermal response and the reference thermal response, and surface conditions module 36 predicts corresponding surface conditions based on the thermal characteristics and the predictive analysis model. At 524, surface condition module 36 generates/updates a predictive analytics model based on the thermal characteristics and associated surface conditions. At 528, the surface condition module 36 determines whether additional training is required. If so, the routine 500 proceeds to 532, at 532, the monitoring system 18 receives a selection of new thermal energy parameters and/or surface condition parameters and proceeds to 508. Otherwise, the routine 500 ends.

Referring to FIG. 6, a flow diagram is shown illustrating an example surface condition prediction routine 600 executed by the surface condition module 36. By way of example, the surface condition prediction routine 600 may be executed when the semiconductor processing system 10-1 is operating at periodic intervals and/or at other various time intervals. At 604, the thermal control system 30 provides thermal energy to the component 12, and at 608 the thermal response determination module 32 determines the thermal response of the component 12. At 612, the characteristics module 34 determines thermal characteristics of the component 12 based on the thermal response and the reference thermal response. At 616, the surface condition module 36 predicts the corresponding surface condition based on the thermal characteristics and the predictive analysis model.

At 620, monitoring system 18 determines whether the predicted surface condition activates alarm module 40. If so, the routine 600 proceeds to 624. Otherwise, if the alarm module 40 is not activated at 620, the routine 600 ends. At 624, the surface condition verification module 42 determines whether the predicted surface condition corresponds to an actual surface condition of the component 12. If so, the routine 600 proceeds to 632, where the surface condition verification module 42 determines 632 that the predictive analysis model is accurate. If the predicted surface conditions at 624 do not correspond to the actual surface conditions of the component 12, the surface condition verification module 42 updates the predictive analytical model at 628.

It should be appreciated that the routines 500, 600 are merely example routines and that other routines may be performed by the monitoring system 18.

Although the monitoring system 18 is described herein as predicting a surface condition of the component 12 of the semiconductor processing system 10, it should be understood that the monitoring system 18 may be used in other environments and is not limited to the semiconductor processing system 10 described herein.

The monitoring system of the present disclosure detects relative changes in emissivity, creating a predictive preventative maintenance solution based on the detected relative changes in emissivity. Preventative/predictive maintenance may be performed based on actual changes to various components in the semiconductor processing system rather than any preventative maintenance schedule. Thus, the monitoring system may reduce maintenance costs and down time and increase equipment runtime.

Unless otherwise expressly stated herein, all numbers indicating mechanical/thermal properties, compositional percentages, dimensions and/or tolerances, or other characteristics, are to be understood as modified by the word "about" or "approximately" in describing the scope of this disclosure. Such modifications are desirable for a variety of reasons, including industrial practice, materials, manufacturing and assembly tolerances, and testing capabilities.

As used herein, the phrase at least one of a, B, and C should be interpreted to mean a logic (a or B or C) using a non-exclusive logical or, and should not be interpreted to mean "at least one of a, at least one of B, and at least one of C.

The description of the disclosure is merely exemplary in nature and, thus, variations that do not depart from the gist of the disclosure are intended to be within the scope of the disclosure. Such variations are not to be regarded as a departure from the spirit and scope of the disclosure.

In the figures, the direction of the arrows generally represents the flow of information (such as data or instructions) of interest to the diagram, as indicated by the arrows. For example, when element a and element B exchange various information, but the information transferred from element a to element B is related to the illustration, an arrow may point from element a to element B. This one-way arrow does not mean that no other information is transmitted from element B to element a. Further, for information sent from element a to element B, element B may send a request for the information or an acknowledgement of receipt of the information to element a.

In this application, the term controller or module may refer to, belong to, or include: an Application Specific Integrated Circuit (ASIC); digital, analog, or hybrid analog/digital discrete circuits; digital, analog, or hybrid analog/digital integrated circuits; a combinational logic circuit; a Field Programmable Gate Array (FPGA); processor circuitry (shared, dedicated, or group) that executes code; memory circuitry (shared, dedicated, or group) that stores code executed by the processor circuitry; other suitable hardware components that provide the described functionality, such as, but not limited to, mobile drives and systems, transceivers, routers, input/output interface hardware, and the like; or a combination of some or all of the above, such as in a system on a chip.

The term memory is a subset of the term computer readable medium. The term computer-readable medium as used herein does not include transitory electrical or electromagnetic signals propagating through a medium, such as on a carrier wave; thus, the term computer-readable medium may be considered tangible and non-transitory. Non-limiting examples of the non-transitory tangible computer-readable medium are non-volatile memory circuits (such as flash memory circuits, erasable programmable read-only memory circuits, or mask read-only circuits), volatile memory circuits (such as static random access memory circuits or dynamic random access memory circuits), magnetic storage media (such as analog or digital tapes or hard drives), and optical storage media (such as CDs, DVDs, or blu-ray discs).

The apparatus and methods described herein may be implemented in part or in whole by a special purpose computer created by configuring a general purpose computer to perform one or more specific functions contained in a computer program. The functional blocks, flowchart elements and other elements described above are used as software specifications, which can be translated into a computer program by the routine work of a skilled technician or programmer.

Claims

1. A method, comprising:

providing thermal energy to the component;

determining a thermal response of the component in response to providing the thermal energy;

determining a thermal characteristic of the component based on a reference thermal response and the thermal response; and

predicting a surface condition of the component based on the thermal characteristic and a predictive analysis model, wherein the predictive analysis model correlates the thermal characteristic of the component to an estimated surface condition of the component.

2. The method of claim 1, wherein the thermal characteristic is based on a difference between the reference thermal response and the thermal response.

3. The method of claim 1, wherein the thermal characteristic is an emissivity of the component, a thermal coupling between different regions of the component, a thermal gain of the component, a resistance-temperature dependence of the component, a gas convection coupling of the component, or a combination thereof.

4. The method of claim 1, wherein providing the thermal energy to the component further comprises increasing the thermal energy provided to the component.

5. The method of claim 1, wherein providing the thermal energy to the component further comprises reducing the thermal energy provided to the component.

6. The method of claim 1, wherein the surface condition represents an amount of material accumulated on a surface of the component.

7. The method of claim 1, wherein the thermal response is a rate of heat energy dissipation by the component.

8. The method of claim 1, further comprising varying at least one of an intensity and a duration of the thermal energy to create a thermal signature of the component, wherein the thermal signature is an image representation of the thermal response.

9. The method of claim 8, further comprising determining the thermal characteristic of the component based on a reference thermal signature and the thermal signature.

10. The method of claim 1, wherein the component is selected from the group consisting of a wall of a semiconductor processing chamber, a liner of the semiconductor processing chamber, a showerhead of the semiconductor processing chamber, a lid of the semiconductor processing chamber, a wall of a fluid heating conduit, a heater surface, and a heater jacket.

11. The method of claim 1, further comprising measuring a temperature of the component during a predetermined period of time to determine the thermal response.

12. The method of claim 11, further comprising determining an energy dissipation of the component based on a change in the temperature of the component during the predetermined period of time.

13. The method of claim 12, further comprising determining a change in emissivity of the component based on a change in temperature of the component during the predetermined period of time.

14. The method of claim 1, wherein the thermal response of the component is determined in response to a temperature of the component being equal to a predetermined temperature.

15. A system, comprising:

a component;

a thermal control system configured to provide thermal energy to the component; and

a controller configured to:

determining a thermal response of the component in response to providing the thermal energy, wherein the thermal response is a rate of dissipation of the thermal energy of the component;

determining a thermal characteristic of the component based on a difference between a reference thermal response and the thermal response, wherein the reference thermal response is a dissipation reference rate of thermal energy of the component in response to providing the thermal energy; and is

Predicting an amount of material accumulation on the component surface based on the thermal characteristic and a predictive analysis model, wherein the predictive analysis model correlates the thermal characteristic of the component to an estimated surface condition of the component.

16. The system of claim 15, wherein the thermal characteristic is an emissivity of the component, a thermal coupling between different regions of the component, a thermal gain of the component, a resistance-temperature dependence of the component, a gas convection coupling of the component, or a combination thereof.

17. The system of claim 15, wherein the component is selected from the group consisting of a wall of a semiconductor processing chamber, a liner of the semiconductor processing chamber, a showerhead of the semiconductor processing chamber, a lid of the semiconductor processing chamber, a wall of a fluid heating conduit, a heater surface, and a heater jacket.

18. The system of claim 15, wherein the thermal control system further comprises a heater configured to provide the thermal energy to the component.

19. The system of claim 15, wherein the predictive analysis model is generated during a training routine.

20. The system of claim 15, wherein the component is a semiconductor processing system component.